A battery thermal management control method, a battery management system and an electric vehicle
By using deep learning prediction models of vehicle BMS and cloud BMS, full life cycle thermal management of batteries is achieved, solving the problem of charging or driving delays in batteries at extremely low temperatures in existing technologies, and improving user experience and battery life.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- DR OCTOPUS INTELLIGENT TECH (SHANGHAI) CO LTD
- Filing Date
- 2022-12-26
- Publication Date
- 2026-05-12
AI Technical Summary
Existing battery thermal management methods restrict charging or driving at extremely low temperatures, extending user waiting time, and do not manage the battery throughout its entire life cycle, affecting user experience and lifespan.
By working in tandem with the vehicle's BMS and the cloud-based BMS, deep learning prediction models are used to predict the optimal operating temperature and dormancy time of the battery, controlling battery heating or cooling to achieve thermal management throughout its entire lifecycle.
Reduce user wait time, improve user experience, and extend battery life.
Smart Images
Figure CN115959006B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of electric vehicle technology, and more specifically, to a battery thermal management control method, a battery management system, and an electric vehicle. Background Technology
[0002] The main function of a BMS (Battery Management System) is to intelligently manage and maintain each battery cell, prevent overcharging and over-discharging, extend battery life, and monitor battery status. As one of the core components of new energy vehicles, the operating temperature of the power battery system directly affects its performance and lifespan; a suitable operating temperature allows the battery to maximize its energy output.
[0003] In existing technologies, the Battery Management System (BMS) manages battery thermally by adjusting the battery temperature when the vehicle enters charging or driving mode. Heating is activated when the temperature is below a threshold and deactivated when the temperature reaches the set temperature. Conversely, cooling is activated when the temperature is above the threshold and deactivated when the temperature reaches the set temperature. However, this thermal management method has several drawbacks: when the battery temperature is extremely low, the BMS limits the requested charging current to zero or restricts power output, preventing the vehicle from charging or driving normally. Charging or normal driving can only resume when the temperature rises to the optimal charging / discharging temperature, a process that takes time and increases user waiting time, thus reducing user experience. Furthermore, this thermal management method only operates when the vehicle enters charging or driving mode, not throughout the battery's entire lifespan, which is detrimental to extending battery lifespan.
[0004] Therefore, how to perform battery thermal management more reliably is a technical problem that needs to be solved. Summary of the Invention
[0005] This application provides a battery thermal management control method, a battery management system, and an electric vehicle for more reliable battery thermal management.
[0006] In a first aspect, a battery thermal management control method is provided, applied to a system including a vehicle BMS and a cloud-based BMS, the method comprising:
[0007] The vehicle BMS sends temperature data and duration data to the cloud BMS. The temperature data includes the pre-calibrated optimal operating temperature of the battery at the factory and the current ambient temperature. The duration data includes a first duration and a second duration.
[0008] The vehicle BMS receives the current optimal battery operating temperature and the current target sleep duration returned from the cloud BMS. The current optimal battery operating temperature is obtained by the cloud BMS after inputting the temperature data into a first preset deep learning prediction model, and the current target sleep duration is obtained by the cloud BMS after inputting the duration data into a second preset deep learning prediction model.
[0009] The vehicle BMS determines the difference between the current SOC value of the battery and the preset minimum SOC value;
[0010] The vehicle BMS controls the battery's operating temperature based on the difference, the current optimal battery operating temperature, and the current target sleep duration.
[0011] The first duration is determined based on the required duration for each time within a preset historical time interval. The required duration is the time required for the battery to be heated or cooled from its lowest temperature after dormancy to its optimal operating temperature under the current ambient temperature. The second duration is determined based on the dormancy duration of the vehicle BMS for each time within the preset historical time interval.
[0012] A second aspect provides a battery management system, the battery management system comprising:
[0013] The sending module is used to send temperature data and duration data to the cloud BMS. The temperature data includes the pre-calibrated optimal operating temperature of the battery at the factory and the current ambient temperature. The duration data includes a first duration and a second duration.
[0014] The receiving module is used to receive the current optimal battery operating temperature and the current target sleep duration returned from the cloud BMS. The current optimal battery operating temperature is obtained by the cloud BMS after inputting the temperature data into a first preset deep learning prediction model, and the current target sleep duration is obtained by the cloud BMS after inputting the duration data into a second preset deep learning prediction model.
[0015] The determination module is used to determine the difference between the current SOC value of the battery and the preset minimum SOC value;
[0016] The control module is used to control the operating temperature of the battery based on the difference, the current optimal operating temperature of the battery, and the current target sleep duration;
[0017] The first duration is determined based on the required duration for each time within a preset historical time interval. The required duration is the time required for the battery to be heated or cooled from its lowest temperature after hibernation to its optimal operating temperature under the current ambient temperature. The second duration is determined based on the hibernation duration of the battery management system for each time within the preset historical time interval.
[0018] Thirdly, an electric vehicle is provided, including a battery management system as described in the second aspect.
[0019] By applying the above technical solutions, the vehicle's BMS sends temperature data and duration data to the cloud-based BMS. The temperature data includes the pre-calibrated optimal battery operating temperature and the current ambient temperature, while the duration data includes a first duration and a second duration. The vehicle's BMS receives the current optimal battery operating temperature and the current target sleep duration returned from the cloud-based BMS. The current optimal battery operating temperature is obtained by the cloud-based BMS after inputting the temperature data into a first preset deep learning prediction model, and the current target sleep duration is obtained by the cloud-based BMS after inputting the duration data into a second preset deep learning prediction model. The vehicle's BMS determines the difference between the battery's current SOC value and a preset minimum SOC value. Based on this difference and the current optimal battery operating temperature, the vehicle's BMS... The battery's operating temperature is controlled by the operating temperature and the current target sleep duration. The first duration is determined based on the required duration for each time interval within a preset historical time interval. The required duration is the time required for the battery to heat or cool from its lowest temperature after sleep to its optimal operating temperature under the current ambient temperature. The second duration is determined based on the sleep duration of each time interval of the vehicle's BMS within the preset historical time interval. By automatically waking up the vehicle's BMS to heat or cool the battery, the battery can reach its optimal operating temperature in advance, reducing user waiting time and improving user experience. Furthermore, by predicting the target sleep duration of the vehicle's BMS and the optimal operating temperature of the battery through the cloud-based BMS, thermal management can be achieved throughout the battery's entire life cycle, thus improving battery lifespan. Attached Figure Description
[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0021] Figure 1 A schematic flowchart of a battery thermal management control method proposed in an embodiment of the present invention is shown;
[0022] Figure 2 A schematic flowchart of a battery thermal management control method according to another embodiment of the present invention is shown;
[0023] Figure 3 A schematic diagram illustrating the principle of the first preset deep learning prediction model in an embodiment of the present invention is shown.
[0024] Figure 4 A schematic diagram illustrating the principle of the second preset deep learning prediction model in an embodiment of the present invention is shown;
[0025] Figure 5 A schematic diagram of a battery management system proposed in an embodiment of the present invention is shown. Detailed Implementation
[0026] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0027] This application provides a battery thermal management control method, applied to a system including a vehicle BMS and a cloud-based BMS, such as... Figure 1 As shown, the method includes the following steps:
[0028] In step S101, the vehicle BMS sends temperature data and duration data to the cloud BMS. The temperature data includes the pre-calibrated optimal operating temperature of the battery at the factory and the current ambient temperature. The duration data includes a first duration and a second duration.
[0029] In this embodiment, the vehicle BMS is installed in the vehicle, and the cloud BMS is installed in the cloud. Both the vehicle BMS and the cloud BMS are equipped with wireless communication modules, which communicate with each other. These wireless communication modules can be based on any communication method such as WiFi, 4G, or 5G. Temperature data includes the pre-calibrated optimal battery operating temperature and the current ambient temperature. The current ambient temperature is the temperature of the operating environment in which the vehicle is located. Since different optimal battery operating temperatures and different current ambient temperatures will affect the optimal battery operating temperature, for example, if the current ambient temperature is low, the optimal battery operating temperature should be higher than the optimal battery operating temperature, and vice versa. The vehicle BMS can periodically send the pre-calibrated optimal battery operating temperature and the current ambient temperature to the cloud BMS, which can then determine the current optimal battery operating temperature based on these parameters.
[0030] The duration data includes a first duration and a second duration. The first duration is determined based on the required duration for each occurrence within a preset historical time interval. This required duration is the time needed for the battery to heat or cool from its lowest temperature after hibernation to its optimal operating temperature under the current ambient temperature. The first duration can be the average of the required durations within the preset historical time interval, or it can be the required duration for a specific occurrence within the preset historical time interval (such as the most recent or a random occurrence). The second duration is determined based on the hibernation duration of the vehicle BMS within the preset historical time interval. The second duration can be the average of the hibernation durations within the preset historical time interval, or it can be the hibernation duration for a specific occurrence within the preset historical time interval (such as the most recent or a random occurrence). The hibernation duration is the time from when the vehicle BMS enters hibernation mode to when it wakes up again.
[0031] Different first durations and different second durations will affect the target sleep duration. The vehicle BMS can periodically send the first duration and the second duration to the cloud BMS, and the cloud BMS can determine the current target sleep duration based on the first duration and the second duration.
[0032] In order to accurately obtain the optimal operating temperature of the battery at the factory, in some embodiments of this application, the calibration process of the optimal operating temperature of the battery at the factory includes: conducting charge-discharge cycle tests on the battery at different temperature ranges, different SOC value ranges and different charge-discharge rates, obtaining a correspondence table characterizing the relationship between temperature, SOC value and charge-discharge rate based on the test results, and determining the optimal operating temperature of the battery at the factory based on the correspondence table.
[0033] In this embodiment, the calibration process is performed before the vehicle leaves the factory. Multiple temperature ranges (e.g., temperatures ranging from -20℃ to 60℃ in 10℃ increments) and multiple SOC (State of Charge) value ranges are set. Then, the battery is subjected to charge-discharge cycle tests under different temperature ranges, different SOC value ranges, and different charge-discharge rates to obtain a temperature-SOC-charge-discharge rate MAP table, i.e., the corresponding relationship table. The optimal operating temperature of the battery at the factory can be determined based on this corresponding relationship table.
[0034] Those skilled in the art may also use other methods to calibrate the optimal operating temperature of the battery at the factory, such as through simulation tests, which does not affect the scope of protection of this application.
[0035] In step S102, the vehicle BMS receives the current optimal battery operating temperature and the current target sleep duration returned from the cloud BMS. The current optimal battery operating temperature is obtained by the cloud BMS after inputting the temperature data into a first preset deep learning prediction model, and the current target sleep duration is obtained by the cloud BMS after inputting the duration data into a second preset deep learning prediction model.
[0036] In this embodiment, the cloud-based BMS is pre-configured with a first preset deep learning prediction model and a second preset deep learning prediction model. After receiving temperature and duration data, the cloud-based BMS inputs the battery's optimal factory operating temperature and the current ambient temperature into the first preset deep learning prediction model, and determines the current optimal battery operating temperature based on the output of the first preset deep learning prediction model. The cloud-based BMS inputs the first duration and the second duration into the second preset deep learning prediction model, and determines the current target sleep duration based on the output of the second preset deep learning prediction model. The first and second preset deep learning prediction models can be based on deep learning algorithms such as CNN (Convolutional Neural Networks), RNN (Recurrent Neural Networks), or Generative Adversarial Networks. The first and second preset deep learning prediction models can use the same deep learning algorithm or different deep learning algorithms.
[0037] In step S103, the vehicle BMS determines the difference between the current SOC value of the battery and the preset minimum SOC value.
[0038] In this embodiment, since heating or cooling the battery consumes its remaining capacity, but it is not allowed to completely deplete the remaining capacity, a preset minimum SOC value is set. The difference between the current SOC value and the preset minimum SOC value is determined, and this difference represents the available capacity of the battery for heating or cooling.
[0039] In step S104, the vehicle BMS controls the battery operating temperature based on the difference, the current optimal battery operating temperature, and the current target sleep duration.
[0040] In this embodiment, the vehicle BMS can decide whether to wake up automatically based on the difference and the current target sleep duration. After waking up automatically, it can control the battery's operating temperature based on the difference and the current optimal battery operating temperature.
[0041] To more accurately control the battery's operating temperature, in some embodiments of this application, the vehicle BMS controls the battery's operating temperature based on the difference, the current optimal battery operating temperature, and the current target sleep duration. Specifically:
[0042] If the difference is not less than the target required capacity and the current sleep time of the vehicle BMS reaches the current target sleep time, the vehicle BMS will wake up automatically and start the heating or cooling function according to the current temperature of the battery, and stop the heating or cooling function when the operating temperature reaches the current optimal operating temperature of the battery.
[0043] If the difference is greater than zero and less than the target required capacity, and the current sleep time reaches the current target sleep time, the vehicle BMS will wake up automatically and start the heating function or the cooling function according to the current temperature of the battery, and stop the heating function or the cooling function when the difference is zero.
[0044] The target required capacity is the battery capacity required to heat or cool the battery from the current temperature to the current optimal operating temperature of the battery.
[0045] In this embodiment, the target required capacity is the battery capacity required to heat or cool the battery from its current temperature to its current optimal operating temperature. If the difference is not less than the target required capacity, it indicates that the current SOC value is greater than the preset minimum SOC value, allowing for self-wake-up. Furthermore, the battery's current remaining capacity is sufficient to reach its current optimal operating temperature. When the current sleep duration reaches the target sleep duration, the vehicle BMS automatically wakes up and initiates the heating or cooling function based on the battery's current temperature. The heating or cooling function stops when the operating temperature reaches the current optimal operating temperature. The heating or cooling function is a built-in function of the vehicle BMS and is existing technology; the specific working principle of heating or cooling will not be elaborated here.
[0046] If the difference is greater than zero and less than the target required capacity, it means that the current SOC value is greater than the preset minimum SOC value, and self-wake-up is possible. However, the current remaining capacity of the battery is not enough to make the battery reach the current optimal operating temperature. Therefore, when the current sleep time reaches the current target sleep time, the vehicle BMS will wake up automatically and start the heating or cooling function according to the current temperature of the battery. The heating or cooling function will stop when the difference is zero.
[0047] Understandably, if the current temperature of the battery is the optimal operating temperature, the vehicle's BMS will not activate the heating or cooling functions.
[0048] To ensure battery reliability, in some embodiments of this application, the method further includes:
[0049] If the difference is less than zero and the current sleep duration reaches the current target sleep duration, the vehicle BMS remains in sleep mode.
[0050] In this embodiment, if the difference is less than zero, it means that the current SOC value is less than the preset minimum SOC value. In order to ensure the safety of the battery, the vehicle BMS will no longer perform self-wake-up.
[0051] In order to accurately determine whether the current sleep duration has reached the current target sleep duration, in some embodiments of this application, when the vehicle BMS enters the sleep state, it starts a countdown based on the current target sleep duration, and the vehicle BMS determines that the current sleep duration has reached the current target sleep duration when the countdown is zero.
[0052] In this embodiment, the vehicle BMS determines the countdown time based on the current target sleep duration. The countdown starts when entering the sleep state. When the countdown reaches zero, it can be determined that the current sleep duration has reached the current target sleep duration. Since it is no longer necessary to compare the current sleep duration with the current target sleep duration, it can determine whether the current sleep duration has reached the current target sleep duration more efficiently and accurately.
[0053] By applying the above technical solutions, the vehicle's BMS sends temperature data and duration data to the cloud-based BMS. The temperature data includes the pre-calibrated optimal battery operating temperature and the current ambient temperature, while the duration data includes a first duration and a second duration. The vehicle's BMS receives the current optimal battery operating temperature and the current target sleep duration returned from the cloud-based BMS. The current optimal battery operating temperature is obtained by the cloud-based BMS after inputting the temperature data into a first preset deep learning prediction model, and the current target sleep duration is obtained by the cloud-based BMS after inputting the duration data into a second preset deep learning prediction model. The vehicle's BMS determines the difference between the battery's current SOC value and a preset minimum SOC value. Based on this difference and the current optimal battery operating temperature, the vehicle's BMS... The battery's operating temperature is controlled by the operating temperature and the current target sleep duration. The first duration is determined based on the required duration for each time interval within a preset historical time interval. The required duration is the time required for the battery to heat or cool from its lowest temperature after sleep to its optimal operating temperature under the current ambient temperature. The second duration is determined based on the sleep duration of each time interval of the vehicle's BMS within the preset historical time interval. By automatically waking up the vehicle's BMS to heat or cool the battery, the battery can reach its optimal operating temperature in advance, reducing user waiting time and improving user experience. Furthermore, by predicting the target sleep duration of the vehicle's BMS and the optimal operating temperature of the battery through the cloud-based BMS, thermal management can be achieved throughout the battery's entire life cycle, thus improving battery lifespan.
[0054] To further illustrate the technical concept of this invention, the technical solution of this invention will now be described in conjunction with specific application scenarios.
[0055] This application provides a battery thermal management control method, applied to a system including a vehicle BMS and a cloud-based BMS. The method includes the following steps:
[0056] Step 1: The vehicle BMS sends the pre-calibrated optimal battery operating temperature Temp0 and the current ambient temperature Temp1 to the cloud BMS.
[0057] Step 2: The cloud-based BMS inputs the battery's factory optimal operating temperature Temp0 and the current ambient temperature Temp1 into the first preset deep learning prediction model, determines the current optimal battery operating temperature Temp based on the output of the first preset deep learning prediction model, and returns the current optimal battery operating temperature Temp to the vehicle BMS.
[0058] like Figure 3 As shown, the first preset deep learning prediction model employs a deep learning algorithm containing an input layer, a hidden layer, and an output layer, comprising three neurons: H1, H2, and H3. Taking Temp = f1(Temp0, Temp1) as an example, the input information is the battery's optimal factory operating temperature Temp0 and the current ambient temperature Temp1, and the output is the current optimal battery operating temperature Temp.
[0059] The computation process from the input layer to the hidden layer is as follows:
[0060] H11 = Temp0 * W T0H11 +Temp1*W T1H11
[0061] H21 = Temp0 * W T0H21 +Temp1*W T1H21
[0062] H31 = Temp0 * W T0H31 +Temp1*W T1H31
[0063] In the formula, W T0H11 W represents the weights of Temp0 from the input layer to the first neuron H1 in the hidden layer. T1H11 W represents the weights of Temp1 from the input layer to the first neuron H1 in the hidden layer. T0H21 W represents the weights of Temp0 from the input layer to the second neuron H2 in the hidden layer. T1H21 W represents the weights of Temp1 from the input layer to the second neuron H2 in the hidden layer. T0H31 W represents the weights of Temp0 from the input layer to the third neuron H3 in the hidden layer. T1H31 The weights of Temp1 from the input layer to the third neuron H3 in the hidden layer.
[0064] Use activation function have to:
[0065]
[0066]
[0067]
[0068] In the formula, H11 out H21 is the output value of the first neuron H1. out H31 is the output value of the second neuron H2. out This is the output value of the third neuron, H3.
[0069] The computation process from the hidden layer to the output layer is as follows:
[0070] H = H11 out *W TH12 +H21 out *W TH22 +H 31out *W TH32 In the formula, W TH12 W represents the weights of the first neuron H1 from the hidden layer to the output layer. TH22 W represents the weights of the second neuron H2 from the hidden layer to the output layer. TH32 The weights for the third neuron H3 from the hidden layer to the output layer.
[0071] Use activation function Determine the optimal operating temperature of the current battery:
[0072]
[0073] Step 3: The vehicle BMS calculates the first duration (Time1) and the second duration (Time2) and sends them to the cloud BMS. The first duration (Time1) is determined based on the required duration for each occurrence within a preset historical time interval. The required duration is the time required for the battery to heat or cool from its lowest temperature (Temp2) after hibernation to its optimal operating temperature (Temp) at the current ambient temperature (Temp1). The second duration (Time2) is determined based on the hibernation duration of each occurrence within the preset historical time interval from the vehicle BMS.
[0074] Step 4: The cloud-based BMS inputs the first duration Time1 and the second duration Time2 into the second preset deep learning prediction model, determines the current target sleep duration Time based on the output of the second preset deep learning prediction model, and returns the current target sleep duration Time to the vehicle BMS.
[0075] like Figure 4The diagram shown illustrates the principle of the second preset deep learning prediction model. The specific principle of the second preset deep learning prediction model is similar to that of the first preset deep learning prediction model mentioned above, and will not be repeated here.
[0076] Step 5: The vehicle's BMS controls the battery's operating temperature based on the current optimal battery operating temperature (Temp), the current target sleep time (Time), and the battery's current SOC value. The specific process is as follows... Figure 2 As shown, it includes the following steps:
[0077] In step S201, the vehicle BMS enters a sleep state and starts a countdown based on the current target sleep duration.
[0078] Step S202: Check if the countdown is zero. If yes, proceed to step S203; otherwise, proceed to step S202.
[0079] Step S203: Is the difference not less than the target required capacity? If yes, proceed to step S204; otherwise, proceed to step S206.
[0080] In this step, the difference is the difference between the current SOC value and the preset minimum SOC value.
[0081] Step S204: The vehicle BMS wakes up automatically and starts the heating or cooling function.
[0082] Step S205: Has the operating temperature reached the current optimal operating temperature of the battery? If yes, proceed to step S210; otherwise, proceed to step S205.
[0083] Step S206: Is the difference greater than zero and less than the target required capacity? If yes, proceed to step S207; otherwise, proceed to step S208.
[0084] Step S207: The vehicle BMS wakes up automatically, starts the heating or cooling function, and proceeds to step S209.
[0085] Step S208: The vehicle BMS remains in sleep mode.
[0086] Step S209: Is the difference zero? If yes, proceed to step S210; otherwise, proceed to step S209.
[0087] In step S210, the vehicle BMS stops the heating or cooling function.
[0088] By applying the above technical solutions, combined with users' daily driving habits and the climate environment in which the vehicle is used, the cloud-based BMS predicts the future operating conditions of the vehicle, enabling the vehicle's BMS to wake up in advance and activate the battery's heating or cooling functions. This allows the battery to reach its optimal operating temperature earlier, reducing user waiting time and enabling thermal management throughout the battery's entire life cycle, thus improving battery lifespan.
[0089] This application also proposes a battery management system, such as... Figure 5 As shown, the battery management system includes:
[0090] The sending module 501 is used to send temperature data and duration data to the cloud BMS. The temperature data includes the pre-calibrated optimal operating temperature of the battery at the factory and the current ambient temperature. The duration data includes a first duration and a second duration.
[0091] The receiving module 502 is used to receive the current optimal battery operating temperature and the current target sleep duration returned from the cloud BMS. The current optimal battery operating temperature is obtained by the cloud BMS after inputting the temperature data into a first preset deep learning prediction model, and the current target sleep duration is obtained by the cloud BMS after inputting the duration data into a second preset deep learning prediction model.
[0092] The determination module 503 is used to determine the difference between the current SOC value of the battery and the preset minimum SOC value;
[0093] Control module 504 is used to control the operating temperature of the battery based on the difference, the current optimal operating temperature of the battery, and the current target sleep duration;
[0094] The first duration is determined based on the required duration for each time within a preset historical time interval. The required duration is the time required for the battery to be heated or cooled from its lowest temperature after hibernation to its optimal operating temperature under the current ambient temperature. The second duration is determined based on the hibernation duration of the battery management system for each time within the preset historical time interval.
[0095] In specific application scenarios, control module 504 is specifically used for:
[0096] If the difference is not less than the target required capacity and the current sleep time of the battery management system reaches the current target sleep time, the battery management system will wake up automatically and start the heating or cooling function according to the current temperature of the battery. The heating or cooling function will stop when the operating temperature reaches the current optimal operating temperature of the battery.
[0097] If the difference is greater than zero and less than the target required capacity, and the current sleep time reaches the current target sleep time, the battery management system will wake up automatically and start the heating function or the cooling function according to the current temperature of the battery, and stop the heating function or the cooling function when the difference is zero.
[0098] The target required capacity is the battery capacity required to heat or cool the battery from the current temperature to the current optimal operating temperature of the battery.
[0099] In specific application scenarios, control module 504 is also used for:
[0100] If the difference is less than zero and the current sleep duration reaches the current target sleep duration, the battery management system is kept in sleep mode.
[0101] In specific application scenarios, the battery management system also includes a countdown module, used for:
[0102] When the battery management system enters a sleep state, a countdown is started based on the current target sleep duration. The control module determines that the current sleep duration has reached the current target sleep duration when the countdown reaches zero.
[0103] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.
Claims
1. A battery thermal management control method, characterized in that, Applied to systems including vehicle BMS and cloud-based BMS, the method includes: The vehicle BMS sends temperature data and duration data to the cloud BMS. The temperature data includes the pre-calibrated optimal battery operating temperature and the current ambient temperature. The duration data includes a first duration and a second duration. The calibration process for the optimal battery operating temperature includes: conducting charge-discharge cycle tests on the battery at different temperature ranges, different SOC value ranges, and different charge-discharge rates; obtaining a correspondence table characterizing the relationship between temperature, SOC value, and charge-discharge rate based on the test results; and determining the optimal battery operating temperature based on the correspondence table. The vehicle BMS receives the current optimal battery operating temperature and the current target sleep duration returned from the cloud BMS. The current optimal battery operating temperature is obtained by the cloud BMS after inputting the temperature data into a first preset deep learning prediction model, and the current target sleep duration is obtained by the cloud BMS after inputting the duration data into a second preset deep learning prediction model. The vehicle BMS determines the difference between the current SOC value of the battery and the preset minimum SOC value; The vehicle BMS controls the battery's operating temperature based on the difference, the current optimal battery operating temperature, and the current target sleep duration. The first duration is determined based on the required duration for each time within a preset historical time interval. The required duration is the time required for the battery to be heated or cooled from its lowest temperature after dormancy to its optimal operating temperature under the current ambient temperature. The second duration is determined based on the dormancy duration of the vehicle BMS for each time within the preset historical time interval.
2. The method as described in claim 1, characterized in that, The vehicle BMS controls the battery's operating temperature based on the difference, the current optimal battery operating temperature, and the current target sleep duration, specifically as follows: If the difference is not less than the target required capacity and the current sleep time of the vehicle BMS reaches the current target sleep time, the vehicle BMS will wake up automatically and start the heating or cooling function according to the current temperature of the battery, and stop the heating or cooling function when the operating temperature reaches the current optimal operating temperature of the battery. If the difference is greater than zero and less than the target required capacity, and the current sleep time reaches the current target sleep time, the vehicle BMS will wake up automatically and start the heating function or the cooling function according to the current temperature of the battery, and stop the heating function or the cooling function when the difference is zero. The target required capacity is the battery capacity required to heat or cool the battery from the current temperature to the current optimal operating temperature of the battery.
3. The method as described in claim 2, characterized in that, The method further includes: If the difference is less than zero and the current sleep duration reaches the current target sleep duration, the vehicle BMS remains in sleep mode.
4. The method as described in claim 2, characterized in that, When the vehicle BMS enters a sleep state, it starts a countdown based on the current target sleep duration. The vehicle BMS determines that the current sleep duration has reached the current target sleep duration when the countdown reaches zero.
5. A battery management system, characterized in that, The battery management system includes: The sending module is used to send temperature data and duration data to the cloud-based BMS. The temperature data includes the pre-calibrated optimal operating temperature of the battery at the factory and the current ambient temperature. The duration data includes a first duration and a second duration. The calibration process for the optimal operating temperature of the battery at the factory includes: conducting charge-discharge cycle tests on the battery under different temperature ranges, different SOC value ranges, and different charge-discharge rates; obtaining a correspondence table characterizing the relationship between temperature, SOC value, and charge-discharge rate based on the test results; and determining the optimal operating temperature of the battery at the factory based on the correspondence table. The receiving module is used to receive the current optimal battery operating temperature and the current target sleep duration returned from the cloud BMS. The current optimal battery operating temperature is obtained by the cloud BMS after inputting the temperature data into a first preset deep learning prediction model, and the current target sleep duration is obtained by the cloud BMS after inputting the duration data into a second preset deep learning prediction model. The determination module is used to determine the difference between the current SOC value of the battery and the preset minimum SOC value; The control module is used to control the operating temperature of the battery based on the difference, the current optimal operating temperature of the battery, and the current target sleep duration; The first duration is determined based on the required duration for each time within a preset historical time interval. The required duration is the time required for the battery to be heated or cooled from its lowest temperature after hibernation to its optimal operating temperature under the current ambient temperature. The second duration is determined based on the hibernation duration of the battery management system for each time within the preset historical time interval.
6. The battery management system as described in claim 5, characterized in that, The control module is specifically used for: If the difference is not less than the target required capacity and the current sleep time of the battery management system reaches the current target sleep time, the battery management system will wake up automatically and start the heating or cooling function according to the current temperature of the battery. The heating or cooling function will stop when the operating temperature reaches the current optimal operating temperature of the battery. If the difference is greater than zero and less than the target required capacity, and the current sleep time reaches the current target sleep time, the battery management system will wake up automatically and start the heating function or the cooling function according to the current temperature of the battery, and stop the heating function or the cooling function when the difference is zero. The target required capacity is the battery capacity required to heat or cool the battery from the current temperature to the current optimal operating temperature of the battery.
7. The battery management system as described in claim 6, characterized in that, The control module is also specifically used for: If the difference is less than zero and the current sleep duration reaches the current target sleep duration, the battery management system is kept in sleep mode.
8. The battery management system as described in claim 6, characterized in that, The battery management system also includes a countdown module for: When the battery management system enters a sleep state, a countdown is started based on the current target sleep duration. The control module determines that the current sleep duration has reached the current target sleep duration when the countdown reaches zero.
9. An electric vehicle, characterized in that, Including the battery management system as described in any one of claims 5-8.